1. Nitrogen‐Containing Functional Groups Dominate the Molecular Absorption of Water‐Soluble Humic‐Like Substances in Air From Nanjing, China Revealed by the Machine Learning Combined FT‐ICR‐MS Technique.
- Author
-
Hong, Yihang, Zhang, Yan‐Lin, Bao, Mengying, Fan, Mei‐Yi, Lin, Yu‐Chi, Xu, Rongshuang, Shu, Zhiyang, Wu, Ji‐Yan, Cao, Fang, Jiang, Hongxing, Cheng, Zhineng, Li, Jun, and Zhang, Gan
- Subjects
FUNCTIONAL groups ,MACHINE learning ,CYCLOTRON resonance ,ABSORPTION coefficients ,LIGHT absorption ,DEEP learning - Abstract
The light absorption capacity of water‐soluble humic‐like substances (HULISWS) at the molecular level is crucial for reducing the uncertainties in modeling the radiative forcing. This study proposed a machine learning approach to allocate the light absorption coefficient at 365 nm (Abs365) of HULISWS into 8084 Fourier transform‐ion cyclotron resonance mass spectrometry (FT‐ICR‐MS) detached molecular markers and their potential functional groups. The ML model showed an acceptable uncertainty (<5%) to the whole Abs365 value based on the prediction errors. The results showed that five critical light‐absorbing molecules (C4H6O4NS, C8H6O4NS, C11H15O3N2, C12H15O3N2, and C19H21O6) could explain 74% (±3%) of the variation of Abs365 in the winter, whereas no crucial light‐absorbing molecules were found in the summer. Besides, the nitrogen‐containing functional groups were found to dominate (61% ± 8%) the molecular absorption near the 365 nm of the spectrum. This work illustrated how functional groups affect the absorption of HULISWS, providing critical information for future research of HULISWS on the molecular level. Plain Language Summary: Water‐soluble humic‐like substances are a crucial light‐absorbing component of fine particulate matter in China. Understanding the crucial light‐absorbing chromophores of the light‐absorbing mixtures was helpful in controlling the global warming event. In this study, CHON and CHONS species were found to dominate the light absorption coefficient of water‐soluble humic‐like substances in Nanjing by combining the machine learning algorithm with the FT‐ICR‐MS technique. Then, the dominant light‐absorbing molecules were further combined with the UV‐Vis spectra from the chemical database to further estimate the light‐absorbing functional groups. Our results indicated that nitrogen‐containing functional groups dominate the light‐absorbing ability of water‐soluble humic‐like substances. Key Points: Appropriate synthetic minority over‐sampling based few‐shot learning could decipher the light‐absorbing molecules from a small data setC4H6O4NS, C8H6O4NS, C11H15O3N2, C12H15O3N2, and C19H21O6 dominate the Abs365 of HULISWS in NanjingNitrogen‐containing functional groups dominate the light‐absorbing ability of HULISWS at a micro‐level [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF